Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    adverbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     위한
    -0.07
     Expenses
    -0.07
     expenses
    -0.06
     dav
    -0.06
    /storage
    -0.06
    .detail
    -0.06
    .Att
    -0.06
    /connect
    -0.06
     UIT
    -0.06
    /UI
    -0.06
    POSITIVE LOGITS
     correctly
    0.07
    Josh
    0.06
    '));
↵
    0.06
     Orr
    0.06
    ła
    0.06
     equality
    0.06
    UF
    0.06
    ocumented
    0.06
     survivor
    0.06
     Rena
    0.06
    Act Density 0.024%

    No Known Activations